WPT technology is therefore considered a promising solution to address the energy supply and access problems of Internet of Things (IoT) devices . The receiver device then extracts electrical energy from the field to power electrical devices, effectively reducing the reliance on wires and batteries. The technology operates by generating a time-varying electromagnetic field, which transfers energy to a receiver device in the spatial field. Wireless power transfer (WPT) technology, in particular, allows for the transfer of electrical energy without the need for conductors as transmission links. To mitigate this issue, researchers have proposed energy harvesting (EH) mechanisms . However, one of the major challenges associated with computation offloading is the limited energy of mobile devices powered by batteries, which can impact the local execution or offloading of tasks to MEC servers, resulting in tasks dropping due to timeouts. It has been widely recognized as an effective solution to resolve the computational constraints of mobile devices . Simulation results show that the proposed HDMAPPO strategy outperforms other baseline algorithms in terms of average task latency, energy consumption, and discard rate.Ĭomputation offloading is a widely studied area in mobile computing which aims to address the computational demands of mobile devices by leveraging additional computing resources, thereby reducing their computational workloads. To address these sub-problems, we propose a computational offloading framework based on multi-agent proximal policy optimization (MAPPO), where each agent generates actions based on its observed private state to avoid the problem of action space explosion due to the increasing number of user devices. The complexity of the problem is reduced by decoupling. The proposed strategy decomposes the computational offloading problem into two sub-problems: a high-level task offloading location selection problem and a low-level task offloading ratio problem. In this paper, we investigate the computational offloading problem in multi-user multi-server MEC systems with energy harvesting, aiming to minimize both system latency and energy consumption by optimizing task offload location selection and task offload ratio.We propose a hierarchical computational offloading strategy based on multi-agent reinforcement learning (MARL). Multi-access edge computing (MEC) is a novel computing paradigm that leverages nearby MEC servers to augment the computational capabilities of users with limited computational resources.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |